The utility differs from the desktop application in that it contains no graphical user interface and works only from the command line. This is useful to integrate the Text-To-Speech process to other applications, for example.

1. Balabolka is freeware, so you may create audio files for free. But if you use the commercial voices, you need to contact the developers of the voice and purchase the license for commercial use/audio broadcast. The audio distribution license will allow you to use speech in YouTube videos.
2. We only want to TTS voices, just install them all then use, Balabolka to play them. Cortana is simple just double click on cortana.reg and cortana2.reg and hit yes. It only makes it so your system can use her voice like windows narrator or balabolka. Also don't rename any files or you might just bugger up the installers like that Data1.cab file.

Comment,subscribe, and like! The links are below. Instructions: Press ok when the pop us shows what ur downloading, I didnt p. In Win10, you can download TTS voices in system setting Or, you can download some third party voices, such as IVONA and VW notice, they are not for free.

The utility handles various command line parameters to be able to read text aloud or save as an audio file. The command line options use the syntax 'balcon [options ..]', all parameters must be separated by a space. Options can appear in any order on the command line so long as they are paired with their related parameters. Use the 'balcon -?' command line to get help on the command line syntax and parameters.

-l

Prints the list of available voices.

-g

Prints the list of available audio output devices.

-ftext_file

Sets the name of the input text file.

-wwave_file

Sets the name of the output file in WAV format. If the option is specified, an audio file will be created. Otherwise, text will be read aloud.

-nvoice_name

Sets the voice name (the part of the name will be enough). If the option is not specified, the voice, defined by the option -id, or the default voice of Windows will be used.

-idinteger

Sets Locale ID for the voice. Locale ID is the language code, assigned by Microsoft (for example, '1033' or '0x0409' for 'English - United States'). The program will choose the first voice with specified Locale ID from the list of voices. If the option is not specified, the voice, defined by the option -n, or the default voice of Windows will be used.

-m

Prints the parameters of the voice.

-binteger

Sets the audio output device by its index. The index of the default audio device is 0.

-rtext

Sets the audio output device by its name.

-c

Takes the text input from clipboard.

-ttext_line

Text input can be taken from the command line.

-i

Takes the text input from STDIN.

-o

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: writes sound data to STDOUT.
If the option is specified, the option -w is ignored.

-sinteger

SAPI 4: sets the speed in a range of 0 to 100 (no default value).
SAPI 5 and Microsoft Speech Platform: sets the speed in a range of -10 to 10 (the default is 0).

-pinteger

SAPI 4: sets the pitch in a range of 0 to 100 (no default value).
SAPI 5 and Microsoft Speech Platform: sets the pitch in a range of -10 to 10 (the default is 0).

-vinteger

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: sets the volume in a range of 0 to 100 (the default is 100).

-einteger

Sets the length of pauses between sentences (in milliseconds). The default is 0.

-ainteger

Sets the length of pauses between paragraphs (in milliseconds). The default is 0.

-dfile_name

Uses a dictionary for pronunciation correction (*.BXD, *.REX or *.DIC). The command line may contain few options -d.

-k

Kills other copies of the application in the computer's memory.

-ka

Kills the active copy of the application in the computer's memory.

-pr

Make pause or resume reading aloud by the active copy of the application. The action is the same as for the context menu item 'Pause'/'Resume'.

-q

Adds the utility to a queue. The application will wait until other copies of the utility have finished.

-lrc

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: creates the LRC file (a file format that synchronizes text with an audio file), if the option -w or -o is specified.

-srt

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: creates the SRT file (SubRip text file format), if the option -w or -o is specified.

-vsfile_name

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: sets the name of output text file with visemes, if the option -w is specified. A viseme is the mouth shape that corresponds to a particular speech sound. SAPI supports the list of 21 visemes. This list is based on the original Disney visemes. The application will create the audio file and then read it aloud to get visemes and their timecodes.

-sub

Text will be processed as subtitles.
The option may be useful, when the options -i or -c are specified.

-tray

Shows the application's icon in the system tray. This allows to view the progress of the task. The context menu item 'Stop' can be used to stop the process.

-lninteger

Selects a line from the text file by using of a line number. The line numbering starts at '1'. The interval of numbers can be used for selecting of more than one line (for example, '26-34'). The command line may contain few options -ln.

-frinteger

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: sets the output audio sampling frequency in kHz (8, 11, 12, 16, 22, 24, 32, 44, 48). If the option is not specified, the default value for the selected voice will be used.

-btinteger

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: sets the output audio bit depth (8 or 16). If the option is not specified, the default value for the selected voice will be used.

-chinteger

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: sets the output audio channel mode (1 or 2). If the option is not specified, the default value for the selected voice will be used.

-? or -h

Prints the list of available command line options.

--encodingencoding or -encencoding

Sets the input text encoding ('ansi', 'utf8' or 'unicode'). The default is 'ansi'.

--silence-begininteger or -sbinteger

Sets the length of silence at the beginning of the audio file (in milliseconds). The default is 0.

--silence-endinteger or -seinteger

Sets the length of silence at the end of the audio file (in milliseconds). The default is 0.

--lrc-lengthinteger

Sets the maximal length of text lines for the LRC file (in characters).

--lrc-fnamefile_name

Sets the name of the LRC file. The option may be useful, when the option -o is specified.

--lrc-encencoding

Sets the encoding for the LRC file ('ansi', 'utf8' or 'unicode'). The default is 'ansi'.

--lrc-offsetinteger

Sets the time shift for the LRC file (in milliseconds).

--lrc-artisttext

Sets the ID tag for the LRC file: artist.

--lrc-albumtext

Sets the ID tag for the LRC file: album.

--lrc-titletext

Sets the ID tag for the LRC file: title.

--lrc-authortext

Sets the ID tag for the LRC file: author.

--lrc-creatortext

Sets the ID tag for the LRC file: creator of the LRC file.

--srt-lengthinteger

Sets the maximal length of text lines for the SRT file (in characters).

--srt-fnamefile_name

Sets the name of the SRT file. The option may be useful, when the option -o is specified.

--srt-encencoding

Sets the encoding for the SRT file ('ansi', 'utf8' or 'unicode'). The default is 'ansi'.

--raw

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: output is raw PCM; audio data does not contain the WAV header. The option is used together with the option -o.

--ignore-length or -il

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: omits the length of data in the WAV header. The option is used together with the option -o.

--sub-formattext

Sets the format of subtitles ('srt', 'lrc', 'ssa', 'ass', 'smi' or 'vtt'). If the option is not specified, the format will be determined through the file extension.

--sub-fit or -sf

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: automatically increases the speed to fit time intervals (when the program converts subtitles to audio file).

--sub-maxinteger or -sminteger

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: sets the maximal speed of speech in a range of -10 to 10 (when the program converts subtitles to audio file).

--sub-silvoice_name or -slvoice_name

SAPI 4 and Microsoft Speech Platform: not used.
SAPI 5: sets the voice name for silence tag reading during converting of subtitles (the part of the name will be enough). If an old voice is used to convert subtitles to speech, the created audio file may not contain pauses between text lines. To fix that problem, an additional modern voice can be used to read the silence tag.

--delete-file or -df

Removes the text file, when job is done. The option is used together with the option -f.

--ignore-square-brackets or -isb

Ignore text in [square brackets].

--ignore-curly-brackets or -icb

Ignore text in {curly brackets}.

--ignore-angle-brackets or -iab

Ignore text in <angle brackets>.

--ignore-round-brackets or -irb

Ignore text in (round brackets).

--ignore-url or -iu

Ignore URLs.

--ignore-comments or -ic

Ignore comments in text. Single-line comments start with // and continue until the end of the line. Multiline comments start with /* and end with */.

--voice1-namevoice_name

SAPI 4: not used.
SAPI 5 and Microsoft Speech Platform: sets the additional voice name to read foreign words in text (the part of the name will be enough). The option is used together with the option --voice1-langid. Other voices can be set by options --voice2-name, --voice3-name, etc.

--voice1-langidlanguage_id

Sets the language ID for foreign words in text. The option is used together with the option --voice1-name. The command line may contain more than one option --voice1-langid. Also an option may contain a comma-separated list of IDs.
The list of supported language IDs is based on ISO 639-1 codes: am, ar, az, ba, bg, be, ca, cs, cu, cv, da, de, el, en, es, et, eu, fi, fil, fr, ja, he, hi, hr, hu, hy, it, gn, gu, ka, kk-Cyr, kk-Lat, kn, ko, ky, lo, lt, lv, mk, no, pl, pt, ro, ru, sk, sl, sr-Cyr, sr-Lat, sv, tg, th, tr, tt, uk, zh.

--voice1-rateinteger

Sets the rate for the additional voice in a range of -10 to 10 (the default is 0).

--voice1-pitchinteger

Sets the pitch for the additional voice in a range of -10 to 10 (the default is 0).

--voice1-volumeinteger

Sets the volume for the additional voice in a range of 0 to 100 (the default is 100).

--voice1-roman

Use the default voice to read Roman numerals in text. If text with non-Latin characters contains Roman numerals, the application will not change a voice to read them.

--voice1-digit

Use the default voice to read numbers in text. If the option is not specified, the additional voice will read numbers near foreign words.

--voice1-lengthinteger

Set the minimal length of foreign text parts that will be read by the additional voice (in characters).

Create the text file VOICE.TXT with the list of the installed voices:

balcon -l > voice.txt

View the specifications of the Microsoft Anna voice:

balcon -n 'Microsoft Anna' -m

/serif-webplus-x8-serial-key.html.

Convert text from BOOK.TXT to speech and save as BOOK.WAV:

balcon -f 'd:Textbook.txt' -w 'd:Soundbook.wav' -n Emma

Get text from the clipboard, apply rules for the pronunciation correction and read aloud:

balcon -n Callie -c -d 'd:rexrules.rex' -d 'd:dicrules.dic'

Read aloud text from the command line with specified rate and volume:

balcon -n Emily -t 'The text will be read slowly.' -s -5 -v 70

Kill other copies of the application in the computer's memory:

balcon -k

Convert text from STDIN to speech, save as BOOK.WAV and create BOOK.LRC:

balcon -w 'd:book.wav' -i -lrc --lrc-length 80 --lrc-title 'The Lord of the Rings'

Read aloud English and Russian sentences by different voices:

balcon -f 'd:Textbook.txt' -n Kimberly --voice1-name Tatyana --voice1-langid ru

Balabolka Voice Downloads

Convert subtitles to FILM.WAV:

Inpage 2000 download. balcon -f 'd:Textfilm.srt' -w 'd:Soundfilm.wav' -n Laura --sub-fit --sub-max 2

The example of use together with LAME.EXE:

balcon -f d:book.txt -n Heather -o --raw lame -r -s 22.05 -m m -h - d:book.mp3

The example of use together with OGGENC2.EXE:

balcon -f d:book.txt -n Heather -o -il oggenc2 --ignorelength - -o d:book.ogg

The example of use together with WMAENCODE.EXE:

balcon -f d:book.txt -n Heather -o -il wmaencode - d:book.wma --ignorelength

Balabolka Voice Pack

The command line options can be stored as a configuration file 'balcon.cfg' in the same folder as the utility.

The sample configuration file:

The utility may combine options from the configuration file and the command line.

You are free to use and distribute software for noncommercial purposes. For commercial use or distribution, you need to get permission from the copyright holder.

Additional Free Voices For Balabolka

So far we’ve covered the basics of Balabloka. Let’s look at some of the extra things that can be done with Balabolka.

The speech engine for Balabolka relies on an API (Application Program Interface) built into the Windows Operating System. The most current Speech API is SAPI 5. SAPI4 and its voices could be installed on the computer but the voices are not as high quality.

Microsoft David and Microsoft Zira are the default US English voices in Windows 10. Windows 7 had Microsoft Anna 64 bit. There are other voices which can be installed, some free and some purchased. The bit rate, either 32 or 64 bit needs to be matched with the operating system bit rate. Otherwise, the 64-bit programs might not be able to access 32bit voice.

Add Voices To Balabolka

The voice in Balabolka can be changed as we’ve seen, by going to the Menu option for Voice, selecting voice and selecting from the list of recognized voices. This will change the speaking voice. There is a way to change the voice and its properties for selected lines. You can alternate between male and female voices.

Because SAPI5 allows the use of XML tags, there are a number of things we can change including a different voice, Volume, Rate, Pitch, Emph, and Spell.

For example the XML tag to change the voice is <voice required=”Name = voice_name“>. The placeholder, voice_name, is replaced by the full name of the voice, such as Microsoft David Desktop. The completed tag is placed before the line you want the voice to speak. The full tag will look like this:

<Voice Required =”Name = Microsoft David Desktop”>

The video below shows how this will work.

Have fun.